A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 03:30 UTC
[Doc] Fix classification table in list of supported models (#20489)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Jul 4, 2025 at 21:08 UTC
fbd62d87509b34fe17d0f9e81608c6a9b7e2c3ff
1 file changed
+1
docs/models/supported_models.md
+1
@@ -470,6 +470,7 @@ Specified using `--task classify`.
470
|----------------------------------|----------|----------------------------------------|------------------------|-----------------------------|-----------------------|
471
| `JambaForSequenceClassification` | Jamba | `ai21labs/Jamba-tiny-reward-dev`, etc. | ✅︎ | ✅︎ | |
472
| `GPT2ForSequenceClassification` | GPT2 | `nie3e/sentiment-polish-gpt2-small` | | | ✅︎ |
473
+
474
If your model is not in the above list, we will try to automatically convert the model using
475
[as_seq_cls_model][vllm.model_executor.models.adapters.as_seq_cls_model]. By default, the class probabilities are extracted from the softmaxed hidden state corresponding to the last token.
476